FutureMLS-Lab/FlashStates
App
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 7 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 6 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
Inference serving for hybrid attention models (attention plus linear-attention or state-space layers) that reuses cached prefixes for coding-agent sessions. It saves recurrent checkpoints at any token position and manages hybrid state with a cost-aware eviction policy, with an…
Who it's for
ML engineers serving hybrid LLMs with agentic, multi-turn workloads on vLLM
How to use it
Ready-made installers, when the project publishes them, are on its latest release.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up FutureMLS-Lab/FlashStates in my project. Follow its README: https://github.com/FutureMLS-Lab/FlashStates. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/FutureMLS-Lab/FlashStates?ref=badge)Similar repos
- FlashML-org/FreeToken
Edge-native Mixture-of-Experts serving engine for running large open-weight MoE models on consumer hardware. It combines CPU and GPU execution, expert caching and KV cache management, and exposes Anth
- snap-stanford/memorilla
Research code for Memorilla, a memory system that compresses an entire document collection into a fixed set of 16 query-dependent memory tokens fed to a frozen LLM. It includes training recipes, evalu
- basetenlabs/deepseek-ultrafast
An inference engine for DeepSeek-V4.1-Flash on NVIDIA sm_100a and sm_103a GPUs, with 1M-token context and KV cache sharing across servers over RDMA, coordinated through Redis. Includes an OpenAI-compa
- Aevonix/FlashAlign
Applies alignment profiles per request to models served through an inference engine, using abliteration for approved users and channels or keeping a profile active on all routed requests. Works with s
- apple-aiml-research/ml-rsi-inference-bench
A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi
- Picom-code/pico-dgx-ds4
A fork of blaesus/dsgx10 that serves DeepSeek V4.1 Flash across four DGX Spark machines for many concurrent users. It adds sparse-attention changes for 1M context, slot admission by context size, spec